© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42742
    Prev
    Next
    INDEX
    Explanations

    Source code copyright

    np_max-act · gemini-2.0-flash

    The neuron fires on uppercase‐initial tokens in license/header blocks—e.g. company or organization names and version/abbreviation fragments (like “B.V.”, “GmbH”, “KG”, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DEFINED
    -0.07
    STA
    -0.07
    ốn
    -0.07
     nodded
    -0.06
    付け
    -0.06
    (f
    -0.06
     servidor
    -0.06
     школи
    -0.06
    getMessage
    -0.06
    .settings
    -0.06
    POSITIVE LOGITS
     mz
    0.06
     resizing
    0.06
     इसम
    0.06
     Rath
    0.06
     company
    0.06
     Dominic
    0.06
    quito
    0.06
    ystery
    0.06
     Kob
    0.06
     Bav
    0.06
    Activations Density 0.008%

    No Known Activations